Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2408 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.2293. Min Act: -0.1700

Data Index: 6509151 (Open Web Text)

Max Activating Token Index: 767

Text #1

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.1935. Min Act: -0.1700

Data Index: 5896204 (Open Web Text)

Max Activating Token Index: 554

Text #2

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.1810. Min Act: -0.1700

Data Index: 75175 (Open Web Text)

Max Activating Token Index: 415

Text #3

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.1538. Min Act: -0.1700

Data Index: 8116043 (Open Web Text)

Max Activating Token Index: 734

Text #4

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.1740. Min Act: -0.1700

Data Index: 1769605 (Open Web Text)

Max Activating Token Index: 250

Text #5

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.1681. Min Act: -0.1700

Data Index: 1759267 (Open Web Text)

Max Activating Token Index: 126

Text #6

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.1652. Min Act: -0.1700

Data Index: 2529384 (Open Web Text)

Max Activating Token Index: 366

Text #7

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.1377. Min Act: -0.1700

Data Index: 7578833 (Open Web Text)

Max Activating Token Index: 579

Text #8

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.1356. Min Act: -0.1700

Data Index: 4506394 (Open Web Text)

Max Activating Token Index: 633

Text #9

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.1112. Min Act: -0.1700

Data Index: 2692140 (Open Web Text)

Max Activating Token Index: 381

Text #10

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.0983. Min Act: -0.1700

Data Index: 6771042 (Open Web Text)

Max Activating Token Index: 745

Text #11

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.0890. Min Act: -0.1700

Data Index: 7433397 (Open Web Text)

Max Activating Token Index: 709

Text #12

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.0860. Min Act: -0.1700

Data Index: 5207782 (Open Web Text)

Max Activating Token Index: 286

Text #13

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.0927. Min Act: -0.1700

Data Index: 2710707 (Open Web Text)

Max Activating Token Index: 886

Text #14

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.1027. Min Act: -0.1700

Data Index: 6129612 (Open Web Text)

Max Activating Token Index: 496

Text #15

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.1102. Min Act: -0.1700

Data Index: 4452619 (Open Web Text)

Max Activating Token Index: 473

Text #16

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.0883. Min Act: -0.1700

Data Index: 918882 (Open Web Text)

Max Activating Token Index: 441

Text #17

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.0732. Min Act: -0.1700

Data Index: 5981191 (Open Web Text)

Max Activating Token Index: 753

Text #18

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.0506. Min Act: -0.1700

Data Index: 4765690 (Open Web Text)

Max Activating Token Index: 215

Text #19

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.0649. Min Act: -0.1700

Data Index: 7665796 (Open Web Text)

Max Activating Token Index: 785